San Francisco supervisors approved a ban on police using facial recognition technology, making it the first city in the U.S. with such a restriction. SAN FRANCISCO – San Francisco supervisors voted Tuesday to ban the use of facial recognition software by police and other city departments, becoming the first U.S. city to outlaw a rapidly developing technology that has alarmed privacy and civil liberties advocates. The ban is part of broader legislation that requires city departments to establish use policies and obtain board approval for surveillance technology they want to purchase or are using at present. Several other local governments require departments to disclose and seek approval for surveillance technology. "This is really about saying: 'We can have security without being a security state. We can have good policing without being a police state.' And part of that is building trust with the community based on good community information, not on Big Brother technology," said Supervisor Aaron Peskin, who championed the legislation.

In a gallery in downtown Manhattan, people are huddling around four laptops, taking turns to control the apartments of 14 complete strangers. They watch via live video feeds, and respond whenever the residents ask "Someone" to help them. They switch the lights on and off, boil the kettle, put some music on – whatever they can do to oblige. The project, called Someone, is the latest in a series exploring our ever more complicated relationship with technology. It's by the American artist Lauren McCarthy and is a sort of outsourcing of Lauren, an earlier work in which she acted as a real-life Alexa, remotely watching over a home 24 hours a day, responding to its occupants' questions and needs like a flesh and blood version of Amazon's voice-operated virtual assistant. Lauren, a video work, features in AI: More Than Human, which opens this week at the Barbican in London as part of its Life Rewired season, an investigation into what it means to be human in the digital era.

A couple of years ago, there was a joke doing the rounds at technology conferences that AI in business is like teenagers and sex: everyone talks about it, but few actually get it. Is the ribald witticism outdated in 2019? Or has the increased hype enveloping AI that it will magically solve most business problems only further confused executives? So much so they are not engaging with AI's myriad technologies or are left clumsily fumbling with algorithms that fail to perform, while cannier rivals score big. Moreover, has the crucial point that AI in business is best utilised as a means of achieving very specific, narrow-focused objectives, and is not an end point in itself, been obscured by the sheer volume of misleading buzz?

Supervised classification is the most active and emerging research trends in today's scenario. In this view, Artificial Neural Network (ANN) techniques have been widely employed and growing interest to the researchers day by day. ANN training aims to find the proper setting of parameters such as weights ($\textbf{W}$) and biases ($b$) to properly classify the given data samples. The training process is formulated in an error minimization problem which consists of many local optima in the search landscape. In this paper, an enhanced Particle Swarm Optimization is proposed to minimize the error function for classifying real-life data sets. A stability analysis is performed to establish the efficiency of the proposed method for improving classification accuracy. The performance measurement such as confusion matrix, $F$-measure and convergence graph indicates the significant improvement in the classification accuracy.

This paper presents the results of an automated volatile organic compound (VOC) classification process implemented by embedding a machine learning algorithm into an Arduino Uno board. An electronic nose prototype is constructed to detect VOCs from three different fruits. The electronic nose is constructed using an array of five tin dioxide (SnO2) gas sensors, an Arduino Uno board used as a data acquisition section, as well as an intelligent classification module by embedding an approach function which receives data signals from the electronic nose. For the intelligent classification module, a training algorithm is also implemented to create the base of a portable, automated, fast-response, and economical electronic nose device. This solution proposes a portable system to identify and classify VOCs without using a personal computer (PC). Results show an acceptable precision for the embedded approach in comparison with the performance of a toolbox used in a PC. This constitutes an embedded solution able to recognize VOCs in a reliable way to create application products for a wide variety of industries, which are able to classify data acquired by an electronic nose, as VOCs. With this proposed and implemented algorithm, a precision of 99% for classification was achieved into the embedded solution.

We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications such as multi-objective optimization, maximum entropy exploration, and constrained optimization in Markovian environments. In our general setting where a stationary policy could have multiple recurrent classes, the agent faces a subtle yet consequential trade-off in alternating among different actions for balancing the vectorial outcomes. In particular, stationary policies are in general sub-optimal. We propose a no-regret algorithm based on online convex optimization (OCO) tools (Agrawal and Devanur 2014) and UCRL2 (Jaksch et al. 2010). Importantly, we introduce a novel gradient threshold procedure, which carefully controls the switches among actions to handle the subtle trade-off. By delaying the gradient updates, our procedure produces a non-stationary policy that diversifies the outcomes for optimizing the objective. The procedure is compatible with a variety of OCO tools.

In a multiagent system or MAS, due to agent interactions, the agents as a group may make decisions that none of them would make alone; this phenomenon is called emergence. Emergence is characterized by an unanticipated system behavior caused by nonlinear interactions. This paper detects such emergence in a MAS by analyzing agent behaviors across two simple strategies. In the first strategy, agents make decisions based on the local information; in the second strategy, agents make decisions based on global information provided via communication. The proposed method identifies when and how nonlinear interactions cause behavior change, and quantitatively defines emergence based on the change in team performance. It then proves several theorems about emergence in a MAS. It also explores several emergence-related factors like the communication cost and the reward gap quantitatively. Experimental results on several benchmarks demonstrate the promising performance of the proposed framework in detecting emergence in a MAS.

Recently, there has been much attention on tools and techniques for visualizing and acquiring new knowledge and insights. In the VAST 2018 competition, one of the challenges is to discover the fraudulent group of employees at Kasios, a furniture manufacturing company. In this work, we use a graph-based approach that analyzes the data for suspicious employee activities at Kasios. Graph based approaches enable one to handle rich contextual data and provide a deeper understanding of data due to the ability to discover patterns in databases that are not easily found using traditional query or statistical tools. We focus on graph based knowledge discovery in structural data to mine for interesting patterns and anomalies. Our approach first reports the normative patterns in the data, and then discovers any anomalous patterns associated with the previously discovered patterns. For visualizing the suspicious patterns, we also use the enterprise graph database Neo4j. Neo4j Browser provides a way to visualize graph structures.

We present the first automatic emotion detection system for Cantonese. This system classifies input text into eight emotion classes: expectancy, joy, love, surprise, anxiety, sorrow, angry, or hate. While a number of emotion corpora and lexica for Mandarin Chinese have been developed, no emotion dataset is available for Cantonese. We leverage existing Mandarin Chinese emotion resources to build the system, with support from Cantonese-Mandarin lexical mappings from a machine translation system, as well as English-Mandarin lexical mappings to handle code-switching in Cantonese input. Evaluation on a set of Cantonese sentences from social media shows promising results.

Cluster Hire is defined as a problem of hiring a group of experts to maximize profits with the ability to complete multiple projects simultaneously under a budget. It assumes that we have a set of projects which require skills and experts who possess various skills. The process of hiring a group of experts to complete a set of projects under the given conditions is proven to be the NP-hard problem. Individuals expect financial support (i.e.salary) which can be handled by a specific budget that we get, to work on the projects. Addition to maximizing the total profit, we are interested in hiring productive experts who can work many projects concurrently with effective result. Therefore, this paper examines the problem of hiring a cluster of experts, so that the total salary does not exceed more than a given budget and maximizes the total benefit of the projects that a highly productive team can cover collectively. We propose two greedy algorithms to solve this problem with different strategies. We illustrate the effectiveness of our approach by experimenting with the synthetic data sets. The results from a study of the synthetic dataset were compared with Bruteforce and Random Algorithm. It suggested that our proposed both project greedy and expert greedy algorithms performed well regarding both accuracy and run-time.